top of page

HEALTHCARE PEFORMANCE ANALYSIS

The healthcare system in the United States is complex, with countless facilities working tirelessly to deliver patient care. However, hospitals and clinics face constant pressure to improve performance, reduce costs, and provide high-quality care to an increasingly diverse and aging population. Despite advances in medical technology and treatments, understanding the factors that drive patient outcomes, the efficiency of medical care, and financial sustainability remains a challenge for healthcare providers.

​

I undertook this project to address a critical question: How can healthcare facilities better understand their performance, improve patient outcomes, and optimize resource utilization using data analysis? By analyzing detailed healthcare data from multiple facilities across the country, I aimed to provide actionable insights into how hospitals and clinics could improve their services.

​

The data captured key patient demographics, medical conditions, billing information, insurance providers, and hospital admission details. Through rigorous analysis, I explored patterns in patient admissions, the most common medical conditions, and billing trends. I also sought to understand how factors such as age, gender, and insurance providers affected healthcare access and costs. Furthermore, the project aimed to visualize key performance indicators such as patient satisfaction, length of hospital stays, and overall cost-efficiency for each healthcare facility.

​

By combining healthcare data with data visualization techniques, this project aims to give hospital administrators, medical professionals, and policymakers clear insights into the performance of healthcare facilities. The analysis uncovers trends in patient care, reveals opportunities for improving service delivery, and helps create strategies to enhance patient outcomes while managing costs. In an era where healthcare is under the microscope, this project serves as a vital tool for driving data-driven improvements in the health sector.

confident-doctor-hospital-room.jpg

Source of Data

Tools & Files

Microsoft SQL Server - Data Cleaning & Analysis.

PowerBI - Data Visualizations.

Exploratory Data Analysis

EDA involved exploring the healthcare data to answer key questions, such as:

  • Is there a correlation between gender and specific medical conditions?

  • What are the most common medical conditions across different age groups?

  • Which doctors are preferred for specific conditions?

  • What is the average billing amount by each insurance provider?

Key Insights & Findings

  • Correlation Between Gender and Medical Conditions: A slight relationship was observed between gender and specific medical conditions. Asthma had a higher prevalence among males, while arthritis was more common among females. For other medical conditions, the distribution between genders was almost identical. This suggests potential gender-specific risk factors or susceptibilities for certain conditions, particularly for asthma and arthritis.

  • Doctor-to-Patient Ratio: The analysis revealed that the number of doctors was slightly higher than the number of patients. This can positively impact patient care quality and reduce wait times. This ratio is a good indicator of resource availability in the healthcare system.

  • Hospital-to-Patient Proportion: The number of hospitals was found to be proportionate to the number of patients. This proportionality suggests an adequate distribution of healthcare facilities relative to the patient population, which is critical for maintaining accessible healthcare services.

  • Age Group Distribution Across Medical Conditions: Seniors represented the largest age group among patients across almost all medical conditions, followed by adults, young adults, and children. This age distribution highlights the greater healthcare needs of senior populations, likely due to age-related health issues. The data emphasizes the importance of geriatric care and resources within the healthcare system.

  • Insurance Billing Analysis: The average billing amount by insurance provider varied significantly, depending on the medical condition. This variance indicates that certain medical conditions require more expensive treatments or longer hospital stays, leading to higher billing amounts. It also suggests that insurance plans may need to be tailored to better manage the costs associated with specific conditions.

THE DASHBOARD

The data visualization of the analyzed data is shown in the interactive Dashboard. To filter and explore the dashboards from different perspectives, download the PowerBI visualization here!

1. Prioritize Geriatric Care Services: With seniors being the largest patient group, healthcare facilities should focus on geriatric care by offering more specialized units, wellness programs, and preventive services for age-related conditions.

 

2. Insurance Plan Optimization: The variance in billing amounts across providers highlights the need for better insurance management. Tailored plans should cover high-cost treatments effectively, reducing patient expenses and ensuring proper hospital reimbursement.

Recommendations

Conclusion

The analysis of the healthcare dataset provided valuable insights into the relationships between patient demographics, medical conditions, and healthcare resources.

This comprehensive analysis can help inform strategic decisions in the healthcare management and policy-making.

african-american-woman-with-doctor-job-holding-bottle-medicine.jpg

THANK YOU!

Thank you for taking the time out to view my project!

In case you would like to discuss this project further, feel free to email me at:

patriciavalentinedanga@gmail.com.​

bottom of page